commit e766fc2acc91f39c0227f806eb67c03815653914 parent 11029922807904507a66b90434f08ae431b2cf10 Author: Sondre Wold <sondrewold1@gmail.com> Date: Thu, 30 May 2024 15:31:43 +0200 Update README.md Diffstat:
| M | README.md | | | 6 | ++++-- |
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/README.md b/README.md @@ -52,8 +52,7 @@ Run `dataset.py` with `--task` being either `sys`, `subst` or `prod` to create the datasets used for the three experiments from the paper. ### Running the dataset splits -Run `train.py` with your desiered parameters. Consult the `argparse` for an -explantion of the CLI. The file runs the experiments over a set of seeds +`train.py` runs all the experiments on the provided dataset splits. An axplantion of the CLI can be found in the `argpase` method in this file. The file runs the experiments over a set of seeds provided by a white space seperated list to `--seed`. The different models are selected by setting the following model-specific @@ -64,6 +63,9 @@ flags: - Unidirectional: `--unidirectional` - Bidirectional: `--unidirectional --bidirectional` +The hyperparameters we used for the experiments in the paper can be found +in Appendix B. + ### Results Results are logged to Wandb and written to a json file. You can use ```write_results.py``` to aggreate the results across seeds and